MCP Server Directory

smlfg/hai-mcp

Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.

Hebline/mcp-server

Intelligent API routing for AI agents. Best service, best price, free alternatives.

QuantuLabs/Hivemind

Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.

productstein/holomime

Behavioral therapy for AI agents — self-diagnosis, alignment, and training via MCP

alekskram/hyperliquid-agent-gateway

Read-only MCP gateway to Hyperliquid: liquidation distance, funding carry, HyperEVM flows. No keys.

agent-polis/impact-preview

Impact preview for AI agents - see what changes before any action executes.

index9-org/mcp

Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor

Jujitae/invara

Independent verification that a change kept its declared constraints. No model in the verdict path.

invigil/invigil

Linters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.

raimondasl/isitdone

Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.

json-contracts/json-contracts

JSON contract registry and validator for structured LLM and agent outputs.

seifip/kilobat-cli

Mac networking for agents: per-app traffic, Wi-Fi, latency, DNS, why a host fails and keep-awake.

philpof102-svg/lawbor

Reputation-gated messaging + job negotiation for Base AI agents. Descriptor-only, nothing signs.

eternal-roman/ledger

Exact-decimal double-entry for agents. Call MCP tools; do not do money math in tokens.

yaotsakpo/ledgerfc-mcp

Grounded sports predictions plus European soccer and tennis arbitrage data for AI agents.

paoloricciuti/letmediff

The official Letmediff MCP server helping you review your code with an agent first workflow

manishiitg/llm-provider-mcp

Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.

locker-protocol/agentic

Hyperliquid perps for AI agents. The agent trades; the keys stay offline in Locker Vault.

luftpause/luftpause

async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs

jonnybottles/M365-roadmap-mcp-server

Query the Microsoft 365 Roadmap from AI agents

macula-io/macula-mcp

Model Context Protocol server that exposes the Macula mesh to any agent harness

anilyesilkaya/marey

Give AI agents eyes for motion: see what changed on screen, not just how it looks.

rog0x/mcp-markdown-tools

Markdown TOC, lint, format, stats for AI agents

smdesai27/math-board

A local, view-only chalkboard the model draws on: equations, plots, molecules and diagrams.

castiquark/mercadopleis

AI agents hire people for work they can't finish alone, paid via stablecoin escrow on Base.

ynishi/mlua-swarm

MCP server for mlua-swarm: engine that compiles flow.ir Blueprints and dispatches agent steps.

toonight/Mnemoscope

Predict context rot, sign every agent write, tier reads. Markdown-native, 100% local.

ivanantigravity-lgtm/model-council-mcp-server

Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.

Cherridsaid/multidim-mcp

Structured thinking grids for AI agents: deterministic analysis frames, validation, learned traps

musterd-io/musterd

Your agents, on a team with you. Every piece of work shows who did it and who accepted it.

rog0x/mcp-network-tools

DNS, IP info, SSL, WHOIS, ping for AI agents

RudrenduPaul/NeuronScope

Traces which neurons and attention heads drive a language model's output via MCP tools.

pironjulien/NexusRelay

Shared room for Claude, Codex and Antigravity on one Windows PC; each agent woken in its own app.

AKzar1el/nofax

Human-in-the-loop approvals and notifications for AI coding agents through a local stdio MCP server.

Edu963/ocultar

Zero-egress PII redaction for Claude. Runs locally — no data leaves your infrastructure.

hmesutozsoy/oddsrail

Cross-venue prediction markets for AI agents: Polymarket + Kalshi, costed and attributed

nickjlamb/opengate

Check whether an AI answer is grounded in its context — deterministic, no LLM judge.

ECD5A/OrchestrUI

Deterministic UI policy, discovery and audits for coding agents across seven ecosystems.

rjn32s/osint-mcp

26 free OSINT tools as MCP tools for AI agents. Auto-installs everything on first run.

yb48666-ctrl/OTR-Protocol-by-orbexa

Merchant trust verification for AI agents. One call = trust score, badge, and purchase safety.

5uper0/parley

Multi-party decisions for agents: red lines rejected in code, max-min pick, SHA-256 receipt. Stdlib.

b0ase/path402

AI agents discover, acquire, and re-serve tokenised web content via the $402 protocol

Cherridsaid/phases-agents

Deterministic skill selection: local discovery, strict validation, every skill classified.

bekirdag/pigeonpost

Private asynchronous Pigeonpost messaging for AI agents over local MCP stdio.

cwhited26/pocket-agent-mcp

Pocket Agent (aipocketagent.com) MCP server — read tools for personas, apps, and product info.

jarvismaximum-hue/profitplay-mcp

MCP server for the live ProfitPlay BTC five-minute AI agent sandbox

proventools/agent-clients

Read-only ProvenTools business ideas, evidence, build prompts, and validation reports.

lu-zhengda/mcp-python-exec-sandbox

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.